I am trying to test face recognition program using EmguCV. I have my source code form this
http://www.codeproject.com/Articles/239849/Multiple-face-detection-and-recognition-in-real-ti
I try to capture myself and it can recognize me. But when someone whose face isn't trained yet, it recognize as me.
can't anyone help me solve this issue?
It seems there are some inaccuracy using OpenCV.
I'd like to give you two suggestions: 1.Train as many persons as you can. The lager database is, the more accuracy it will be. 2.Try another library. Some more professional facial recognition libraries.
Recently I have found a facial technology Face++. I'm developing an Android APP using their API. It's amazing, easier to use than OpenCV.
I used the same code to implement face recognition and I faced the same issue.
Here's the link that can help you solve your issue. It explains how to modify your EigenRecognizer.cs code
Related
I am looking at using the Kinect version 2 for PC to control an avatar, i.e. apply a skin to the body basics example provided by Microsoft.
The avatar isn't to be used in a game or anything at this point. I simply plan to be able to control the avatar using the Kinect 2 and record to .avi. I have already implemented a demo where I can record the Kinect footage of the skeleton directly to .avi.
After searching I found that it was possible to control an avatar with the original Kinect using XNA game studio. As XNA game studio seems a bit out dated now and I'm unsure if it would be compatible with version 2, would there be an alternative approach? Does anybody know of a project where someone has done this already? Or can anyone suggest a good approach to take to do this?
I have also seen some articles referring to a plugin that lets you use Unity with Kinect 2 but from what I can see I don't believe this is publicly available?
Many thanks for any help.
Yes, the unity plug in works great and its the best out there. the creator its call rumen, he will help you if you need it help but ofcourse you have to pay the plugin 1st. its worth it, it makes kinect way simpler.
I´m trying to work with Kinect SDK 1.7 in WPF and C#. I found some tutorials, but nowhere I cannot find how to work with both hands at once (in my Kinect Region i only see just one hand at any time).
Please can you help me, how to do that? I´d like to this this for zooming in maps!
Thank you very much!
I don't think that making Zoom is easy but there is a way of showing the two hands. You have to go in the source code of the dll and make a small change.
http://social.msdn.microsoft.com/Forums/en-US/7e00d05d-8b97-4838-b3d6-76a71c4d3166/how-to-use-two-hand-cursors-simultaneously-using-kinect-interactions
I have made program that detects the face now what i have to do is Recognize them By googling up i came to know that it is done by EigenObjectRecognizer any one hae used it or can tell me how can i use it?
It has been discussed here already:
Using EigenObjectRecognizer
Or there is a libface library being developed for face detection and recognition:
http://sourceforge.net/projects/libface/
Alex
Are there any C# facial recognition libraries that work? I would like to locate people in my data base by having them stare in a camera :-). This is not used for security or authentication just to help with a quick lookup so if it is good enough to narrow down a list of people that would be a win.
You can look into Microsoft's Face API:
https://www.microsoft.com/cognitive-services/en-us/face-api/documentation/overview
I need to implement face recognition like in orkut album.
In my website when a user uploads a photo and checks the photo in album I need to implement the feature and place rectangles over the faces in photo like in orkut album like in this link.
Please help me to implement this.
Thanks in advance.
You need to use OpenCV, or more specifically, a C# wrapper library for OpenCV.
I think you can implement some (very) basic face detection using OpenCVDotNet, although you should be aware that I don't think it's actively being developed. I just noticed I'm still on the list as a project committer, but I haven't done any work on it for a long time (if ever, can't remember why I got added in the first place).
You should probably go with Emgu CV, which is a much better C# wrapper for OpenCV. It is actively developed, and is compatible with OpenCV 2.0, and has a wider community surrounding it, and the documentation is good enough that you can easily get face detection working pretty quickly.